System, method, and recording medium for corpus pattern paraphrasing

A corpus pattern paraphrasing method, comprising:

• analyzing a corpus of sentences stored in a database to determine regular structures including a plurality of substitute words for verbs expressed as patterns that construct sense disambiguation resources and apply deep learning of the regular structures over the patterns including the constructed sense disambiguation resources;
• creating a plurality of regular rules based on the corpus of sentences analyzed, the plurality of regular rules being created independently to the database to predict a syntactic meaning and a semantic meaning of the corpus of sentences without referring to the database;
• determining a plurality of representative words that represents each class of word of the regular structures;
• and
• aligning word slots of different occurrences of a paraphrase pattern of the classes of words replaced with substitute words and representative words in the paraphrase pattern and a second paraphrase pattern to give a same semantic meaning to the paraphrase pattern and the second paraphrase pattern as a sentence of the corpus of sentences,
• wherein the paraphrase pattern includes exactly one semantic meaning and the rules are congruent to the semantic meaning, and
• wherein the regular rules are syntactic-semantic rules that express linguistic knowledge on how the verbs expressed as patterns are used.

A non-transitory computer-readable recording medium recording a corpus pattern paraphrasing program, the program causing a computer to perform:

• analyzing a corpus of sentences stored in a database to determine regular structures including a plurality of substitute words for verbs expressed as patterns that construct sense disambiguation resources and apply deep learning of the regular structures over the patterns including the constructed sense disambiguation resources;
• creating a plurality of regular rules based on the corpus of sentences analyzed, the plurality of regular rules being created independently to the database to predict a syntactic meaning and a semantic meaning of the corpus of sentences without referring to the database;
• determining a plurality of representative words that represents each class of word of the regular structures;
• and
• aligning word slots of different occurrences of a paraphrase pattern of the classes of words replaced with substitute words and representative words in the paraphrase pattern and a second paraphrase pattern to give a same semantic meaning to the paraphrase pattern and the second paraphrase pattern as a sentence of the corpus of sentences,
• wherein the paraphrase pattern includes exactly one semantic meaning and the rules are congruent to the semantic meaning, and
• wherein the regular rules are syntactic-semantic rules that express linguistic knowledge on how the verbs expressed as patterns are used.